Transferability of radiomic signatures from experimental to human interstitial lung disease

Abstract

Background: Interstitial lung disease (ILD) defines a group of parenchymal lung disorders, characterized by fibrosis as their common final pathophysiological stage. To improve diagnosis and treatment of ILD, there is a need for repetitive non-invasive characterization of lung tissue by quantitative parameters. In this study, we investigated whether CT image patterns found in mice with bleomycin induced lung fibrosis can be translated as prognostic factors to human patients diagnosed with ILD.

Methods: Bleomycin was used to induce lung fibrosis in mice (n_control = 36, n_experimental = 55). The patient cohort consisted of 98 systemic sclerosis (SSc) patients (n_ILD = 65). Radiomic features (n_histogram = 17, n_texture = 137) were extracted from microCT (mice) and HRCT (patients) images. Predictive performance of the models was evaluated with the area under the receiver-operating characteristic curve (AUC). First, predictive performance of individual features was examined and compared between murine and patient data sets. Second, multivariate models predicting ILD were trained on murine data and tested on patient data. Additionally, the models were reoptimized on patient data to reduce the influence of the domain shift on the performance scores.

Results: Predictive power of individual features in terms of AUC was highly correlated between mice and patients (r = 0.86). A model based only on mean image intensity in the lung scored AUC = 0.921 ± 0.048 in mice and AUC = 0.774 (CI95% 0.677-0.859) in patients. The best radiomic model based on three radiomic features scored AUC = 0.994 ± 0.013 in mice and validated with AUC = 0.832 (CI95% 0.745-0.907) in patients. However, reoptimization of the model weights in the patient cohort allowed to increase the model's performance to AUC = 0.912 ± 0.058.

Conclusion: Radiomic signatures of experimental ILD derived from microCT scans translated to HRCT of humans with SSc-ILD. We showed that the experimental model of BLM-induced ILD is a promising system to test radiomic models for later application and validation in human cohorts.

Keywords: bleomycin; interstitial lung disease; lung fibrosis; preclinical imaging; radiomics; systemic sclerosis.

FIGURE 1

Study design. The mice data set (n = 91) was used to discover radiomic patterns predictive of ILD. The discovered patterns were tested in the human validation data set (n = 98). 55 mice were given Bleomycin to induce ILD, whereas 36 mice were given NaCl and served as the control group. The mice were euthanized at day 3, 7, 14, 21, 28, and 35 and scanned with a microCT scanner. Afterward, classification models were trained to predict occurrence of ILD based on images acquired from the scanner. The 98 patients from the validation data set were retrospectively collected. All patients were scanned with HRCT and graded according to the Goh scale of pulmonary fibrosis. The radiomic models built using mice data were tested in patients.

FIGURE 2

Example CT scans of healthy lungs and lungs affected with lung fibrosis. (A) microCT image of a healthy mice lung, (B) microCT image of a mice lung with lung fibrosis, (C) HRCT image of a healthy human lung, (D) HRCT image of a human lung with lung fibrosis. Lung contours marked in different colors show the extent of intra- and interobserver variability in lung segmentations for these two cases.

FIGURE 3

Influence of intra- and interobserver delineation variability on radiomic features stability. Proportion of unstable features stratified by feature type.

FIGURE 4

Relationship between predictive power of radiomic features in mice and patient data sets. (A) AUC distribution stratified by feature type (histogram, gray level co-occurrence matrix (GLCM, n = 26), gray level run length matrix (GLRLM, n = 16), gray level distance zone matrix (GLDZM, n = 16), gray level size zone matrix (GLSZM, n = 16), and neighboring gray level dependence matrix (NGLDM, n = 16). (B–H) Correlation of the AUC between mice and patient groups.

FIGURE 5

Model performance and underlying radiomic features. ROC curves and bar plots of the underlying features. V1 - mean (histogram), V2 - standard deviation (histogram), V4 - skewness (histogram), V5 - kurtosis (histogram), V16 - root mean square (histogram), V108 - gray level non-uniformity normalized (GLSZM), V141 - dependence count non-uniformity (NGLDM).

FIGURE 6

Comparison of feature distribution between mice and patient groups stratified by the ILD stage. V1 - mean (histogram), V2 - standard deviation (histogram), V4 - skewness (histogram), V5 - kurtosis (histogram), V16 - root mean square (histogram), V108 - gray level non-uniformity normalized (GLSZM), V141 - dependence count non-uniformity (NGLDM).